A contrastive learning approach for individual re-identification in a wild fish population

TL;DR

This paper presents a contrastive learning model for identifying individual fish in the wild, achieving high accuracy over varying numbers of image samples, offering a non-invasive alternative to physical tagging.

Contribution

The study introduces a novel contrastive learning approach for fish re-identification, demonstrating its effectiveness on real-world wild fish populations.

Findings

Achieved 0.88 accuracy with 100 images per individual

Model outperforms traditional identification methods

Effective for long-term monitoring of wild fish

Abstract

In both terrestrial and marine ecology, physical tagging is a frequently used method to study population dynamics and behavior. However, such tagging techniques are increasingly being replaced by individual re-identification using image analysis. This paper introduces a contrastive learning-based model for identifying individuals. The model uses the first parts of the Inception v3 network, supported by a projection head, and we use contrastive learning to find similar or dissimilar image pairs from a collection of uniform photographs. We apply this technique for corkwing wrasse, Symphodus melops, an ecologically and commercially important fish species. Photos are taken during repeated catches of the same individuals from a wild population, where the intervals between individual sightings might range from a few days to several years. Our model achieves a one-shot accuracy of 0.35, a 5-shot accuracy of 0.56, and a 100-shot accuracy of 0.88, on our dataset.